© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12971
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuous or repeated actions

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "constantly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemy
    -0.79
    IDA
    -0.75
    nee
    -0.74
    eer
    -0.73
    DragonMagazine
    -0.71
     UM
    -0.69
    rule
    -0.68
    JV
    -0.68
    ahime
    -0.67
    luck
    -0.66
    POSITIVE LOGITS
     fluct
    0.94
     constantly
    0.90
     spaced
    0.90
    entimes
    0.89
     destro
    0.88
     iter
    0.87
     occas
    0.83
     bombard
    0.82
     oscill
    0.82
     replen
    0.81
    Activations Density 0.008%

    No Known Activations